© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27428
    Prev
    Next
    INDEX
    Explanations

    references to formal publications and points within a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.5%
    391
    +0.11
    0.5%
    354
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.03
    232
    +0.11
    0.02
    314
    +0.10
    -0.01
    Negative Logits
     restitution
    -0.76
    EStreamFrame
    -0.75
     fines
    -0.72
     redress
    -0.66
     jaws
    -0.63
     retaliation
    -0.63
     ramifications
    -0.63
     quarantine
    -0.62
     disg
    -0.61
     repercussions
    -0.61
    POSITIVE LOGITS
    iat
    0.85
    uary
    0.83
     Ibid
    0.82
    .;
    0.81
    .,
    0.80
     ib
    0.80
    uations
    0.78
    iary
    0.78
    ividually
    0.77
    ova
    0.76
    Activations Density 0.093%

    No Known Activations